INDEX
Explanations
phrases related to shootings, attacks, and gun control
New Auto-Interp
Neuron Alignment
Index
Value
% of L₁
1842
+0.14
0.4%
964
+0.12
0.3%
468
+0.12
0.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
644
+0.14
0.07
468
+0.12
0.05
964
+0.12
0.05
Negative Logits
<bos>
-1.38
ustainable
-0.52
URERS
-0.49
">//
-0.49
zumal
-0.48
URANCE
-0.47
styleType
-0.47
PicClick
-0.47
sobald
-0.47
folgendes
-0.46
POSITIVE LOGITS
Juf
1.01
Abbé
0.99
Cfr
0.92
akut
0.91
Febru
0.91
Strukt
0.90
ivi
0.89
mikrofon
0.89
centrif
0.88
Keny
0.88
Activations Density 0.799%